Online monitoring system for oil and metal particles of wind power generation gearbox

Abstract

The invention relates to the technical field of gearbox monitoring, in particular to an online monitoring system for oil and metal particles of a wind power generation gearbox. Comprising a central control unit used for generating a monitoring loop according to equipment parameters of a gearbox, and the monitoring loop is provided with a plurality of monitoring points; the monitoring unit comprises a particle sub-module and a plurality of auxiliary sub-modules; the particle monitoring module is arranged on the monitoring loop, and the particle monitoring module is used for collecting data of metal particles in oil; the auxiliary sub-modules are arranged at all monitoring points; the central control unit judges whether a fault early warning instruction is generated or not according to the metal particle data and the oil operation data collected by the monitoring unit. The particle submodule and the auxiliary submodules are additionally arranged, the oil state and the metal particle content of the wind power generation gear box are monitored in real time, early warning is conducted on potential fault risks of the gear box through comprehensive analysis of multiple parameters of the oil, and faults of the gear box are effectively prevented. And the accuracy and reliability of fault diagnosis are improved.

Description

Technical Field

[0001] The present application relates to the technical field of gearbox monitoring, and in particular to an online monitoring system for oil and metal particles in a wind power generation gearbox. Background Art

[0002] With the widespread application of wind energy as a new type of renewable energy, wind turbines have been fully developed. However, wind turbines are usually built in high altitudes such as mountainous areas, Gobi Desert, grasslands, and offshore areas. They are often affected by irregular strong gusts and extreme temperature differences for a long time, and often shut down for maintenance due to failures. As a clean and renewable energy source, wind power generation is becoming increasingly important. One of the key components of a wind turbine is the gearbox, which is responsible for converting the low-speed rotation of the wind wheel into high-speed rotation, thereby driving the generator to generate electricity. The performance of the gearbox directly affects the efficiency and stability of wind power generation.

[0003] Gearboxes are the most vulnerable components in wind turbines. Due to long-term operation in complex environments, gearboxes are prone to wear and fatigue. These problems are often first reflected in the changes in the physical and chemical properties of the lubricating oil and the increase of metal particles in the oil. If the fault is not discovered and solved in time, it is very likely to gradually develop into a serious fault as the wind turbine works for a long time. Because gearboxes are generally installed at high altitudes, the cost of disassembling and returning to the factory for repair is expensive.

[0004] Traditional lubricant monitoring technology often uses a regular offline method to analyze oil samples, but the inspection cycle of this inspection mechanism is relatively long, and it is also prone to secondary oil contamination problems, and the tracking and monitoring mechanism cannot be effectively established.

[0005] Application Contents

[0006] The purpose of this application is: to solve the above-mentioned technical problems, this application provides an online monitoring system for wind power gearbox oil and metal particles, aiming to achieve real-time monitoring of wind power gearboxes and improve the fault warning efficiency of gearboxes.

[0007] In some embodiments of the present application, by adding a particle submodule and multiple auxiliary submodules, the oil state and metal particle content of the wind power gearbox are monitored in real time, and through comprehensive analysis of multiple parameters of the oil, abnormal oil problems are discovered in time, and potential failure risks of the gearbox are warned, effectively preventing the occurrence of gearbox failures. This avoids the problems of long inspection cycles and the proneness to secondary oil contamination in traditional offline detection methods.

[0008] In some embodiments of the present application, by analyzing the changes in the physical and chemical properties and contamination of the oil, the status of the oil and the gearbox is monitored in real time, and timely warnings are given for abnormal operating conditions of the gearbox, thereby improving maintenance efficiency, extending the service life of the gearbox, reducing maintenance costs, and improving the reliability and economy of wind power generation.

[0009] In some embodiments of the present application, a wind power generation gearbox oil and metal particle online monitoring system is provided, comprising:

[0010] A central control unit, used for generating a monitoring loop according to the equipment parameters of the gearbox, wherein the monitoring loop is provided with a plurality of monitoring points;

[0011] A monitoring unit, including a particle submodule and a plurality of auxiliary submodules;

[0012] The particle monitoring module is arranged on the monitoring circuit, and is used to collect metal particle data in the oil;

[0013] The auxiliary submodule is arranged at each monitoring point;

[0014] The central control unit determines whether to generate a fault warning instruction according to the metal particle data and oil operation data collected by the monitoring unit.

[0015] In some embodiments of the present application, the central control unit includes:

[0016] Diagnosis module, used to establish fault diagnosis model;

[0017] A first processing module, used to set working parameters of the particle module;

[0018] The second processing module sets a plurality of auxiliary indicators according to the fault diagnosis model and generates an auxiliary indicator-monitoring point mapping table;

[0019] The second processing module is also used to set the working parameters of each monitoring point according to the auxiliary indicator-monitoring point mapping table;

[0020] The third processing module is used to obtain metal particle data and oil operation data according to a preset feedback time node, and determine whether to generate a fault warning instruction.

[0021] In some embodiments of the present application, the second processing module is further used to:

[0022] Establish a monitoring point sequence A, A = (a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points;

[0023] Set ai as the target monitoring point in turn;

[0024] Set the categories of auxiliary indicators collected at target monitoring points;

[0025] According to the auxiliary indicator category, set the data collection frequency of the auxiliary submodule corresponding to the target monitoring point;

[0026] Set the auxiliary indicator categories of each monitoring point in turn;

[0027] Generate auxiliary indicator-monitoring point mapping table.

[0028] In some embodiments of the present application, the third processing module is further used to:

[0029] Obtain the metal particle data collected by the particle submodule at the current feedback time node;

[0030] Generate the first-level risk value f of the current feedback time node;

[0031] Generate the abnormal evaluation value b of each monitoring point at the current feedback time node;

[0032] Establish an abnormal evaluation value sequence B, B = (b1, b2...b i …b n ), where b i is the abnormal evaluation value of the i-th monitoring point at the current feedback time node;

[0033] Generate a secondary risk value h based on the abnormal evaluation value sequence B;

[0034] Generate the fault risk value c of the current feedback time node according to the first-level risk value f and the second-level risk value h;

[0035] Whether to generate a fault warning instruction is determined according to the fault risk value c.

[0036] In some embodiments of the present application, generating the primary risk value f of the current feedback time node includes:

[0037]

[0038] Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ is the number of particle indicators; β i is the influencing factor of the i-th particle index; j i is the reference value of the i-th particle index generated based on the metal particle data collected at the current feedback time node; j' i is the reference value of the i-th particle index generated based on the metal particle data collected at the last feedback time node; Y(i) is the selection coefficient; if (j i -j' i)>0, Y(i)=1; if (j i -j' i )<0, Y(i)=0.

[0039] In some embodiments of the present application, establishing an abnormal evaluation value series B includes:

[0040] Set ai as the target monitoring point in turn;

[0041] Obtain the monitoring data packet of the target monitoring point at the current feedback time node;

[0042] Generate an abnormal evaluation value b of the target monitoring point according to the monitoring data packet;

[0043]

[0044] Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; m is the amount of data collected in the monitoring data packet; g i is the reference value of the auxiliary index of the target monitoring point collected for the i-th time in the monitoring data package; g' is the standard reference value of the auxiliary index of the target monitoring point; Δg is the average value of all data in the monitoring data package; T(i) is the selection coefficient; if (g i -g')>0, T(i)=1; if (g i -g')<0, T(i)=0;

[0045] Generate the abnormal evaluation value of each monitoring point in turn.

[0046] In some embodiments of the present application, generating the secondary risk value h includes:

[0047]

[0048] Wherein, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; η i is the influencing factor of the ith monitoring point; b' is the preset abnormal evaluation value threshold.

[0049] In some embodiments of the present application, judging whether to generate a fault warning instruction according to the fault risk value c includes:

[0050] Set the compensation coefficient r according to the secondary risk value h;

[0051] Generate a failure risk value c, c = r * h;

[0052] A first fault risk value threshold C1 and a second fault risk value threshold C2 are preset, and C1<C2;

[0053] If c<C1, no fault warning instruction is generated at the current feedback time node;

[0054] If C1<c<C2, the current feedback time node generates a first-level warning instruction;

[0055] If c>C2, the current feedback time node generates a secondary warning instruction.

[0056] In some embodiments of the present application, the compensation coefficient r is set according to the secondary risk value h, including:

[0057] Preset a first risk value interval (H1, H2), a second risk value interval (H2, H3) and a third risk value interval (H3, H4);

[0058] If the secondary risk value h is within the preset first risk value interval, the compensation coefficient r is set to the preset first compensation coefficient r1, that is, r=r1;

[0059] If the secondary risk value h is within the preset second risk value interval, the compensation coefficient r is set to the preset second compensation coefficient r2, that is, r=r2;

[0060] If the secondary risk value h is within the preset third risk value interval, the compensation coefficient r is set to the preset third compensation coefficient r3, that is, r=r3; and 1<r1<r2<r3.

[0061] Compared with the prior art, the online monitoring system for oil and metal particles in a wind power generation gearbox according to the embodiment of the present application has the following beneficial effects:

[0062] By adding particle submodules and multiple auxiliary submodules, the oil status and metal particle content of the wind power gearbox are monitored in real time. Through comprehensive analysis of multiple parameters of the oil, abnormal oil problems can be discovered in time, and potential failure risks of the gearbox can be warned, effectively preventing the occurrence of gearbox failures. This avoids the problems of long inspection cycles and secondary oil contamination that exist in traditional offline detection methods.

[0063] By analyzing the changes in the physical and chemical properties of the oil and contamination, the status of the oil and gearbox is monitored in real time, and early warnings are issued for abnormal operating conditions of the gearbox in a timely manner, thereby improving maintenance efficiency, extending the service life of the gearbox, reducing maintenance costs, and improving the reliability and economy of wind power generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a structural schematic diagram of an online monitoring system for oil and metal particles in a wind power gearbox in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0065] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0066] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0067] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0068] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0069] like Figure 1 As shown, a wind power generation gearbox oil and metal particle online monitoring system according to a preferred embodiment of the present application comprises:

[0070] The central control unit is used to generate a monitoring loop according to the equipment parameters of the gearbox, and a plurality of monitoring points are set on the monitoring loop;

[0071] A monitoring unit, including a particle submodule and a plurality of auxiliary submodules;

[0072] The particle monitoring module is arranged on the monitoring circuit, and is used to collect the metal particle data in the oil;

[0073] Auxiliary submodules are set at each monitoring point;

[0074] The central control unit determines whether to generate a fault warning instruction based on the metal particle data and oil operation data collected by the monitoring unit.

[0075] Specifically, a monitoring loop is established according to the equipment parameters of the gearbox, and the monitoring loop includes: controllable motor, gear pump, controllable proportional valve, abrasive sensor interface, temperature sensor interface, filter, differential pressure relay, moisture sensor interface, heat exchanger cooling unit, viscosity sensor interface, pressure controller, liquid level sensor interface and pressure sensor interface, etc. Through this loop, the characteristic data of the oil such as abrasive, moisture, viscosity, temperature, liquid level and pressure can be fully monitored.

[0076] Specifically, the monitoring points are preferably various interfaces, and corresponding auxiliary submodules are set according to the interface types of the monitoring points.

[0077] Specifically, the auxiliary submodules include but are not limited to: an online moisture monitoring sensor, an online viscosity monitoring sensor, an online temperature monitoring sensor, an online liquid level monitoring sensor, and an online pressure monitoring sensor.

[0078] Specifically, the particle module is preferably an online wear particle monitoring sensor, which adopts the principle of electromagnetic induction, can monitor the iron or non-iron particles in the oil in real time, and provide information on the size and morphology distribution of the particles.

[0079] In a preferred embodiment of the present application, the central control unit includes:

[0080] Diagnosis module, used to establish fault diagnosis model;

[0081] A first processing module, used to set working parameters of the particle module;

[0082] The second processing module sets a plurality of auxiliary indicators according to the fault diagnosis model and generates an auxiliary indicator-monitoring point mapping table;

[0083] The second processing module is also used to set the working parameters of each monitoring point according to the auxiliary indicator-monitoring point mapping table;

[0084] The third processing module is used to obtain metal particle data and oil operation data according to a preset feedback time node, and determine whether to generate a fault warning instruction.

[0085] Specifically, the auxiliary monitoring indicators include but are not limited to parameters such as oil temperature, pressure, viscosity, water content, and acid value.

[0086] Specifically, the second processing module is further used for:

[0087] Establish a monitoring point sequence A, A = (a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points;

[0088] Set ai as the target monitoring point in turn;

[0089] Set the categories of auxiliary indicators collected at target monitoring points;

[0090] According to the auxiliary indicator category, set the data collection frequency of the auxiliary submodule corresponding to the target monitoring point;

[0091] Set the auxiliary indicator categories of each monitoring point in turn;

[0092] Generate auxiliary indicator-monitoring point mapping table.

[0093] Specifically, the data categories required to be collected are set according to the different interface categories of each monitoring point, and the corresponding collection frequency is set according to the data category. The collection frequency refers to the amount of data collection required at two adjacent feedback time nodes.

[0094] Specifically, the categories of collected data include but are not limited to parameters such as oil temperature, pressure, viscosity, moisture content, acid value, etc. Due to the different characteristics of each parameter, the collection frequency can be adjusted specifically to achieve monitoring of multiple parameters of the oil.

[0095] It is understandable that in the above embodiment, by comprehensively analyzing multiple parameters of the oil, abnormal problems of the oil are discovered in time, and potential failure risks of the gearbox are warned, thereby effectively preventing the occurrence of gearbox failures. This improves the accuracy and reliability of fault diagnosis and avoids problems such as long inspection cycles and the proneness to secondary contamination of the oil.

[0096] In a preferred embodiment of the present application, the third processing module is also used for:

[0097] Obtain the metal particle data collected by the particle submodule at the current feedback time node;

[0098] Generate the first-level risk value f of the current feedback time node;

[0099] Generate the abnormal evaluation value b of each monitoring point at the current feedback time node;

[0100] Establish an abnormal evaluation value sequence B, B = (b1, b2...b i …b n ), where b i is the abnormal evaluation value of the i-th monitoring point at the current feedback time node;

[0101] Generate a secondary risk value h based on the abnormal evaluation value sequence B;

[0102] Generate the fault risk value c of the current feedback time node according to the first-level risk value f and the second-level risk value h;

[0103] Whether to generate a fault warning instruction is determined according to the fault risk value c.

[0104] Specifically, the first-level risk value f of the current feedback time node is generated, including:

[0105]

[0106] Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ is the number of particle indicators; β i is the influencing factor of the i-th particle index; j i is the reference value of the i-th particle index generated based on the metal particle data collected at the current feedback time node; j' i is the reference value of the i-th particle index generated based on the metal particle data collected at the last feedback time node; Y(i) is the selection coefficient; if (j i -j' i )>0, Y(i)=1; if (j i -j' i )<0, Y(i)=0.

[0107] Specifically, particle indicators include but are not limited to parameters such as metal particle size, shape and quantity. The larger the first-level risk value, the greater the possibility of operational failure in the current wind turbine gearbox.

[0108] Specifically, all parameters in the model are normalized by presetting the first fixed coefficient and the second fixed coefficient, so that each parameter is within the same value range.

[0109] Specifically, an abnormal evaluation value series B is established, including:

[0110] Set ai as the target monitoring point in turn;

[0111] Obtain the monitoring data packet of the target monitoring point at the current feedback time node;

[0112] Generate an abnormal evaluation value b of the target monitoring point according to the monitoring data packet;

[0113]

[0114] Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; m is the amount of data collected in the monitoring data packet; g i is the reference value of the auxiliary index of the target monitoring point collected for the i-th time in the monitoring data package; g' is the standard reference value of the auxiliary index of the target monitoring point; Δg is the average value of all data in the monitoring data package; T(i) is the selection coefficient; if (g i -g')>0, T(i)=1; if (gi -g')<0, T(i)=0;

[0115] Generate the abnormal evaluation value of each monitoring point in turn.

[0116] Specifically, the larger the abnormal evaluation value, the greater the possibility that the oil parameter category collected at the target monitoring point is abnormal.

[0117] Specifically, by analyzing each monitoring point, the oil's characteristic data such as abrasive particles, moisture, viscosity, temperature, liquid level, pressure, etc. are comprehensively monitored, and then based on the abnormal status of each type of data, early warning of potential failure risks inside the gearbox is issued.

[0118] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter is in the same value range.

[0119] Specifically, the secondary risk value h is generated, including:

[0120]

[0121] Wherein, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; η i is the influencing factor of the ith monitoring point; b' is the preset abnormal evaluation value threshold.

[0122] Specifically, the influencing factor of each monitoring point can be set according to the type of data collected at the monitoring point.

[0123] Specifically, the larger the secondary risk value, the greater the possibility that there are abnormalities in the parameters of the current oil, and the greater the possibility that there is a potential failure risk inside the gearbox.

[0124] It can be understood that in the above embodiments, by analyzing the changes in the physical and chemical properties and contamination of the oil, the status of the oil and the gearbox is monitored in real time, and timely warnings are given for abnormal operating conditions of the gearbox, thereby improving maintenance efficiency, extending the service life of the gearbox, reducing maintenance costs, and improving the reliability and economy of wind power generation.

[0125] In a preferred embodiment of the present application, judging whether to generate a fault warning instruction according to the fault risk value c includes:

[0126] Set the compensation coefficient r according to the secondary risk value h;

[0127] Generate a failure risk value c, c = r * h;

[0128] A first fault risk value threshold C1 and a second fault risk value threshold C2 are preset, and C1<C2;

[0129] If c<C1, no fault warning instruction is generated at the current feedback time node;

[0130] If C1<c<C2, the current feedback time node generates a first-level warning instruction;

[0131] If c>C2, the current feedback time node generates a secondary warning instruction.

[0132] Specifically, the first-level warning instruction means that there is abnormal operation in the current gearbox, which needs to be repaired in time to eliminate potential failure risks and ensure the stable operation of the gearbox. The second-level warning instruction means that there is a failure risk in the current gearbox, which needs to be shut down for maintenance immediately to avoid interference with the overall operation of the system due to operation failures and improve the reliability and service life of the wind turbine.

[0133] Specifically, the compensation coefficient r is set according to the secondary risk value h, including:

[0134] Preset a first risk value interval (H1, H2), a second risk value interval (H2, H3) and a third risk value interval (H3, H4);

[0135] If the secondary risk value h is within the preset first risk value interval, the compensation coefficient r is set to the preset first compensation coefficient r1, that is, r=r1;

[0136] If the secondary risk value h is within the preset second risk value interval, the compensation coefficient r is set to the preset second compensation coefficient r2, that is, r=r2;

[0137] If the secondary risk value h is within the preset third risk value interval, the compensation coefficient r is set to the preset third compensation coefficient r3, that is, r=r3; and 1<r1<r2<r3.

[0138] It can be understood that in the above embodiment, the compensation coefficient is set based on the analysis results of multiple parameters of the oil, so as to dynamically correct the analysis results of the metal particle parameters in the oil, improve the fault diagnosis accuracy of the gearbox, and effectively prevent the occurrence of gearbox failure.

[0139] According to the first concept of this application, by adding a particle submodule and multiple auxiliary submodules, the oil status and metal particle content of the wind power gearbox are monitored in real time, and through comprehensive analysis of multiple parameters of the oil, abnormal oil problems are discovered in time, and potential failure risks of the gearbox are warned, effectively preventing the occurrence of gearbox failures. This avoids the problems of long inspection cycles and easy secondary contamination of oil in traditional offline detection methods.

[0140] According to the second concept of the present application, by analyzing the changes in the physical and chemical properties and contamination of the oil, the status of the oil and the gearbox is monitored in real time, and early warnings are given for abnormal operating conditions of the gearbox in a timely manner, thereby improving maintenance efficiency, extending the service life of the gearbox, reducing maintenance costs, and improving the reliability and economy of wind power generation.

[0141] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. An online monitoring system for oil and metal particles in a wind power generation gearbox, characterized in that: include: A central control unit, used for generating a monitoring loop according to the equipment parameters of the gearbox, wherein the monitoring loop is provided with a plurality of monitoring points; A monitoring unit, including a particle submodule and a plurality of auxiliary submodules; The particle monitoring module is arranged on the monitoring circuit, and is used to collect metal particle data in the oil; The auxiliary submodule is arranged at each monitoring point; The central control unit determines whether to generate a fault warning instruction according to the metal particle data and oil operation data collected by the monitoring unit.

2. The wind power generation gearbox oil and metal particle online monitoring system according to claim 1, characterized in that: The central control unit comprises: Diagnosis module, used to establish fault diagnosis model; A first processing module, used to set working parameters of the particle module; The second processing module sets a plurality of auxiliary indicators according to the fault diagnosis model and generates an auxiliary indicator-monitoring point mapping table; The second processing module is also used to set the working parameters of each monitoring point according to the auxiliary indicator-monitoring point mapping table; The third processing module is used to obtain metal particle data and oil operation data according to a preset feedback time node, and determine whether to generate a fault warning instruction.

3. The wind power generation gearbox oil and metal particle online monitoring system according to claim 2, characterized in that: The second processing module is also used for: Establish a monitoring point sequence A, A = (a1, a2…a i …a n ), where a i is the i-th monitoring point; n is the number of monitoring points; Set ai as the target monitoring point in turn; Set the categories of auxiliary indicators collected at target monitoring points; According to the auxiliary indicator category, set the data collection frequency of the auxiliary submodule corresponding to the target monitoring point; Set the auxiliary indicator categories of each monitoring point in turn; Generate auxiliary indicator-monitoring point mapping table.

4. The wind power generation gearbox oil and metal particle online monitoring system according to claim 3, characterized in that: The third processing module is also used for: Obtain the metal particle data collected by the particle submodule at the current feedback time node; Generate the first-level risk value f of the current feedback time node; Generate the abnormal evaluation value b of each monitoring point at the current feedback time node; Establish an abnormal evaluation value sequence B, B = (b1, b2...b i …b n ), where b i is the abnormal evaluation value of the i-th monitoring point at the current feedback time node; Generate a secondary risk value h based on the abnormal evaluation value sequence B; Generate the fault risk value c of the current feedback time node according to the first-level risk value f and the second-level risk value h; Whether to generate a fault warning instruction is determined according to the fault risk value c.

5. The wind power generation gearbox oil and metal particle online monitoring system according to claim 4, characterized in that: Generate the first-level risk value f of the current feedback time node, including: Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ is the number of particle indicators; β i is the influencing factor of the i-th particle index; j i is the reference value of the i-th particle index generated based on the metal particle data collected at the current feedback time node; j' i is the reference value of the i-th particle index generated based on the metal particle data collected at the last feedback time node; Y(i) is the selection coefficient; if (j i -j' i )>0, Y(i)=1; if (j i -j' i )<0, Y(i)=0.

6. The wind power generation gearbox oil and metal particle online monitoring system according to claim 5, characterized in that: Establish an abnormal evaluation value series B, including: Set ai as the target monitoring point in turn; Obtain the monitoring data packet of the target monitoring point at the current feedback time node; Generate an abnormal evaluation value b of the target monitoring point according to the monitoring data packet; Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; m is the amount of data collected in the monitoring data packet; g i is the reference value of the auxiliary index of the target monitoring point collected for the i-th time in the monitoring data package; g' is the standard reference value of the auxiliary index of the target monitoring point; Δg is the average value of all data in the monitoring data package; T(i) is the selection coefficient; if (g i -g')>0, T(i)=1; if (g i -g')<0, T(i)=0; Generate the abnormal evaluation value of each monitoring point in turn.

7. The wind power generation gearbox oil and metal particle online monitoring system according to claim 6, characterized in that: Generate the secondary risk value h, including: Wherein, e5 is the preset fifth weight coefficient; e6 is the preset sixth weight coefficient; Q5 is the preset fifth fixed coefficient; Q6 is the preset sixth fixed coefficient; η i is the influencing factor of the ith monitoring point; b' is the preset abnormal evaluation value threshold.

8. The wind power generation gearbox oil and metal particle online monitoring system according to claim 7, characterized in that: Determining whether to generate a fault warning instruction according to the fault risk value c includes: Set the compensation coefficient r according to the secondary risk value h; Generate a failure risk value c, c = r * h; A first fault risk value threshold C1 and a second fault risk value threshold C2 are preset, and C1<C2; If c<C1, no fault warning instruction is generated at the current feedback time node; If C1<c<C2, the current feedback time node generates a first-level warning instruction; If c>C2, the current feedback time node generates a secondary warning instruction.

9. The wind power generation gearbox oil and metal particle online monitoring system according to claim 8, characterized in that: The compensation coefficient r is set according to the secondary risk value h, including: Preset a first risk value interval (H1, H2), a second risk value interval (H2, H3) and a third risk value interval (H3, H4); If the secondary risk value h is within the preset first risk value interval, the compensation coefficient r is set to the preset first compensation coefficient r1, that is, r=r1; If the secondary risk value h is within the preset second risk value interval, the compensation coefficient r is set to the preset second compensation coefficient r2, that is, r=r2; If the secondary risk value h is within the preset third risk value interval, the compensation coefficient r is set to the preset third compensation coefficient r3, that is, r=r3; and 1<r1<r2<r3.

Images